create_data.R

n <- 1000
first_name_list <- as.character(wakefield::name(n))
last_name_list <- as.character(wakefield::name(n))
age <- as.numeric(wakefield::age(n))
employment <- as.character(wakefield::employment(n))

# Add misspellings
first_name_list_misspelled <- sapply(
    strsplit(first_name_list, ""),
    function(x) {
        new_letter <- sample(letters, 1)
        position <- sample(seq_len(length(x)), 1)
        x[position] <- new_letter
        paste(x, collapse = "")
    }
)

# Create Datasets
age_data <- data.frame(
    first_name = first_name_list,
    last_name = last_name_list,
    age = age
)

employment_data <- data.frame(
    first_name = first_name_list_misspelled,
    last_name = last_name_list,
    employment = employment
)

# Glimpse Data
dplyr::glimpse(age_data)
dplyr::glimpse(employment_data)

# Save Datasets
readr::write_csv(
    age_data, 
    "data/age_data.csv"
)

readr::write_csv(
    employment_data, 
    "data/employment_data.csv"
)

# Start DB Instance
drv <- duckdb::duckdb()
con <- DBI::dbConnect(drv)

# Connect with Octopus
octopus::view_database(con)